schristoph.online

My Blog Has a Site Map Again

Sat, 17 Oct 2026 00:00:00 +0000

TL;DR: This blog has a site map again, drawn as a pirate’s treasure map, at /map/. Many websites used to have one: a page that linked everything, for lost visitors and for crawlers that found pages largely by following links. Google introduced a machine-readable map in 2005, the other big search engines adopted it in 2006 (sitemap.xml), and the human version slowly faded. Language models got a proposal for one in 2024 (llms.txt). A site with 400+ posts turns out to need all three, one per kind of reader. The treasure map is a single SVG that Hugo fills in at build time.

Lots of websites used to have a page called “Site map”. You probably remember it: a long list of links in the footer, every section of the site on one page. I hadn’t thought about it in years, until this month.

Building Agents That Read the Web Right

Tue, 14 Apr 2026 00:00:00 +0000

The Other Side of the Coin

In a recent article, I made my website AI-agent friendly [1], adding llms.txt, Markdown output, and content negotiation to a Hugo site on AWS. That article was about the producer side: how to serve content that agents can consume efficiently.

But I left a question unanswered: what does it look like from the agent’s perspective?

In this article, I’m building two agents. Same task, same website, same model. The difference: one reads the web the old way, the other uses the infrastructure I just built, different tools, different prompts, the whole consumption path. So this compares two end-to-end approaches, not a single isolated variable. The code is written with the Strands Agents SDK [2], an open-source framework from AWS for building AI agents in Python.

Making My Website AI-Agent Friendly — Here's What Changed

Sun, 22 Mar 2026 00:00:00 +0000

The Test That Failed

Last weekend, I pointed an AI agent at my own blog and asked it a simple question about an article I’d just published, my hands-on experiment with self-reflection on Amazon Bedrock [12]: “What scored 3/15 and why?”

The agent received 29,099 bytes of HTML. After stripping navigation, CSS, scripts, headers, and footers, only about 4,600 characters of actual content remained, 69% of the response was noise. The agent consumed 6,083 input tokens, then gave a confused answer about “personal growth.” It couldn’t find the article content buried in the markup.